scholarly journals Proportional Error Back-Propagation (PEB): Real-Time Automatic Loop Closure Correction for Maintaining Global Consistency in 3D Reconstruction with Minimal Computational Cost

2018 ◽  
Vol 18 (3) ◽  
pp. 86-93 ◽  
Author(s):  
Morteza Daneshmand ◽  
Egils Avots ◽  
Gholamreza Anbarjafari
Keyword(s):  
3D Reconstruction ◽  
Real Time ◽  
Computational Cost ◽  
Back Propagation ◽  
Experimental Conditions ◽  
Loop Closure ◽  
Error Back Propagation ◽  
Correction Technique ◽  
Global Consistency ◽  
Wide Range

AbstractThis paper introduces a robust, real-time loop closure correction technique for achieving global consistency in 3D reconstruction, whose underlying notion is to back-propagate the cumulative transformation error appearing while merging the pairs of consecutive frames in a sequence of shots taken by an RGB-D or depth camera. The proposed algorithm assumes that the starting frame and the last frame of the sequence roughly overlap. In order to verify the robustness and reliability of the proposed method, namely, Proportional Error Back- Propagation (PEB), it has been applied to numerous case-studies, which encompass a wide range of experimental conditions, including different scanning trajectories with reversely directed motions within them, and the results are presented. The main contribution of the proposed algorithm is its considerably low computational cost which has the possibility of usage in real-time 3D reconstruction applications. Also, neither manual input nor interference is required from the user, which renders the whole process automatic.

scholarly journals A Mathematical Model toward Real-Time Monitoring of Automotive PEM Fuel Cells

2020 ◽  
Author(s):  
Alireza Goshtasbi ◽  
Benjamin L. Pence ◽  
Jixin Chen ◽  
Michael A. DeBolt ◽  
Chunmei Wang ◽  
...  
Keyword(s):  
Fuel Cells ◽  
Real Time ◽  
Computational Cost ◽  
Membrane Electrode Assembly ◽  
Pem Fuel Cells ◽  
Membrane Electrode ◽  
Performance Measurements ◽  
Real Time Monitoring ◽  
Model Calculations ◽  
Wide Range

A computationally efficient model toward real-time monitoring of automotive polymer electrolyte membrane (PEM) fuel cell stacks is developed. Computational efficiency is achieved by spatio-temporal decoupling of the problem, developing a new reduced-order model for water balance across the membrane electrode assembly (MEA), and defining a new variable for cathode catalyst utilization that captures the trade-off between proton and mass transport limitations without additional computational cost. Together, these considerations result in the model calculations to be carried out more than an order of magnitude faster than real time. Moreover, a new iterative scheme allows for simulation of counter-flow operation and makes the model flexible for different flow configurations. The proposed model is validated with a wide range of experimental performance measurements from two different fuel cells. Finally, simulation case studies are presented to demonstrate the prediction capabilities of the model.

scholarly journals A 3D Reconstruction Method Using Multisensor Fusion in Large-Scale Indoor Scenes

Complexity ◽  
2020 ◽  
Vol 2020 ◽  
pp. 1-14
Author(s):  
Panlong Gu ◽  
Fengyu Zhou ◽  
Dianguo Yu ◽  
Fang Wan ◽  
Wei Wang ◽  
...  
Keyword(s):  
3D Reconstruction ◽  
Real Time ◽  
Large Scale ◽  
Reconstruction Method ◽  
Loop Closure ◽  
Mapping Algorithm ◽  
Localization And Mapping ◽  
Indoor Scenes ◽  
Slam Algorithm ◽  
Robot Position

RGBD camera-based VSLAM (Visual Simultaneous Localization and Mapping) algorithm is usually applied to assist robots with real-time mapping. However, due to the limited measuring principle, accuracy, and distance of the equipped camera, this algorithm has typical disadvantages in the large and dynamic scenes with complex lightings, such as poor mapping accuracy, easy loss of robot position, and much cost on computing resources. Regarding these issues, this paper proposes a new method of 3D interior construction, which combines laser radar and an RGBD camera. Meanwhile, it is developed based on the Cartographer laser SLAM algorithm. The proposed method mainly takes two steps. The first step is to do the 3D reconstruction using the Cartographer algorithm and RGBD camera. It firstly applies the Cartographer algorithm to calculate the pose of the RGBD camera and to generate a submap. Then, a real-time 3D point cloud generated by using the RGBD camera is inserted into the submap, and the real-time interior construction is finished. The second step is to improve Cartographer loop-closure quality by the visual loop-closure for the sake of correcting the generated map. Compared with traditional methods in large-scale indoor scenes, the proposed algorithm in this paper shows higher precision, faster speed, and stronger robustness in such contexts, especially with complex light and dynamic objects, respectively.

scholarly journals Deep learning–assisted real-time container corner casting recognition

2019 ◽  
Vol 15 (1) ◽  
pp. 155014771882446
Author(s):  
Jaecheul Lee
Keyword(s):  
Real Time ◽  
Short Term Memory ◽  
Computational Cost ◽  
Back Propagation ◽  
Weather Conditions ◽  
Image Features ◽  
Quality Video ◽  
Image Representations ◽  
Bounding Boxes ◽  
Video Input

Intelligent automated crane systems are now an integral part of container port automation. Accurate corner casting detection boosts the performance of an automated crane system which ultimately automates ships loading and unloading. Existing techniques use various traditional laser-based and vision-based methods for corner casting detection. Challenging weather conditions, varying lighting conditions, light reflections from ground, and container rusting conditions are the main problems that affect the performance of automated cranes. From this line of research, we propose an end-to-end method that takes a low-quality video input and produces bounding boxes around corner castings by applying a recurrent neural network along with long short-term memory units. The expressive image features from GoogLeNet are used to produce intermediate image representations that are further tuned for our system. The proposed system uses back-propagation to allow joint tuning of all components. At least, four cameras are mounted on each crane and input stream is combined into a single image to reduce the computational cost. The proposed system outperforms all existing methods in terms of precision, recall, and F-measure. The proposed method is implemented in a real-time port and produces more than 98% accuracy in all conditions.

scholarly journals ElasticFusion: Real-time dense SLAM and light source estimation

2016 ◽  
Vol 35 (14) ◽  
pp. 1697-1716 ◽  
Author(s):  
Thomas Whelan ◽  
Renato F Salas-Moreno ◽  
Ben Glocker ◽  
Andrew J Davison ◽  
Stefan Leutenegger
Keyword(s):  
Real Time ◽  
Light Source ◽  
Light Sources ◽  
Indoor Environments ◽  
Tracking Accuracy ◽  
Camera Tracking ◽  
Loop Closure ◽  
Novel Approach ◽  
Global Consistency ◽  
Appearance Properties

We present a novel approach to real-time dense visual simultaneous localisation and mapping. Our system is capable of capturing comprehensive dense globally consistent surfel-based maps of room scale environments and beyond explored using an RGB-D camera in an incremental online fashion, without pose graph optimization or any post-processing steps. This is accomplished by using dense frame-to-model camera tracking and windowed surfel-based fusion coupled with frequent model refinement through non-rigid surface deformations. Our approach applies local model-to-model surface loop closure optimizations as often as possible to stay close to the mode of the map distribution, while utilizing global loop closure to recover from arbitrary drift and maintain global consistency. In the spirit of improving map quality as well as tracking accuracy and robustness, we furthermore explore a novel approach to real-time discrete light source detection. This technique is capable of detecting numerous light sources in indoor environments in real-time as a user handheld camera explores the scene. Absolutely no prior information about the scene or number of light sources is required. By making a small set of simple assumptions about the appearance properties of the scene our method can incrementally estimate both the quantity and location of multiple light sources in the environment in an online fashion. Our results demonstrate that our technique functions well in many different environments and lighting configurations. We show that this enables (a) more realistic augmented reality rendering; (b) a richer understanding of the scene beyond pure geometry and; (c) more accurate and robust photometric tracking.

Design of a Switching Control Scheme for Uncertain Objects Based on PID-Type FNN and LS_SVMs

2012 ◽  
Vol 532-533 ◽  
pp. 550-554
Author(s):  
Jun Zhao ◽  
Gan Ping Li ◽  
Chao Dan Zheng
Keyword(s):  
Neural Network ◽  
Back Propagation ◽  
Dynamic Network ◽  
Industrial Process ◽  
Least Square ◽  
Support Vector ◽  
Error Back Propagation ◽  
Control Scheme ◽  
Wide Range ◽  
Controlled Object

PID control schemes have been widely used for industrial process systems over the past several decades. Recently, by combining traditional PID method with modern intelligent control scheme, various control design methodologies have been proposed such as fuzzy PID, neural PID and PID self-tuning by pattern recognition. However, the serious problem here is that the controller parameters must be suitably adjusted according to the property of the controlled object, which often changes gradually. Many identification methods are introduced to cope with this problem, among which the neural network identification is widely used. Generally a static network cannot adequately approximate a dynamic system and the training speed of dynamic network is very slow while the convergence cannot be guaranteed. Moreover, if the range of system uncertainty is very wide, the control performance becomes quite conservative. In this paper, a kind of objects with the wide range of uncertainty is considered and a novel control scheme with switching structure is proposed. A PID-type fuzzy neural network(PFNN) is designed as the controller and optimized by offline quantum-behaved particle swarm optimization(QPSO) with chaos strategy and online error back propagation tuning. The least square support vector machines (LS_SVMs) are introduced to determine the suitable controller parameters by switching and identifying the controlled object. Finally, the simulation results show the feasibility and validity of the proposed method.

scholarly journals Smart Pothole Detection Using Deep Learning Based on Dilated Convolution

Sensors ◽  
2021 ◽  
Vol 21 (24) ◽  
pp. 8406
Author(s):  
Khaled R. Ahmed
Keyword(s):  
Deep Learning ◽  
Real Time ◽  
Computational Cost ◽  
Detection Accuracy ◽  
Setup Cost ◽  
Detection Algorithms ◽  
Dilated Convolution ◽  
Wide Range ◽  
Adequate Accuracy ◽  
Pothole Detection

Roads make a huge contribution to the economy and act as a platform for transportation. Potholes in roads are one of the major concerns in transportation infrastructure. A lot of research has proposed using computer vision techniques to automate pothole detection that include a wide range of image processing and object detection algorithms. There is a need to automate the pothole detection process with adequate accuracy and speed and implement the process easily and with low setup cost. In this paper, we have developed efficient deep learning convolution neural networks (CNNs) to detect potholes in real-time with adequate accuracy. To reduce the computational cost and improve the training results, this paper proposes a modified VGG16 (MVGG16) network by removing some convolution layers and using different dilation rates. Moreover, this paper uses the MVGG16 as a backbone network for the Faster R-CNN. In addition, this work compares the performance of YOLOv5 (Large (Yl), Medium (Ym), and Small (Ys)) models with ResNet101 backbone and Faster R-CNN with ResNet50(FPN), VGG16, MobileNetV2, InceptionV3, and MVGG16 backbones. The experimental results show that the Ys model is more applicable for real-time pothole detection because of its speed. In addition, using the MVGG16 network as the backbone of the Faster R-CNN provides better mean precision and shorter inference time than using VGG16, InceptionV3, or MobilNetV2 backbones. The proposed MVGG16 succeeds in balancing the pothole detection accuracy and speed.

UAV-Based Wireless Telemetry System for the Estimation of Ship Air Wake Patterns

2015 ◽  
Author(s):  
Anil Kumar ◽  
Pinhas Ben-Tzvi ◽  
Murray Snyder
Keyword(s):  
Real Time ◽  
Back Propagation ◽  
Base Station ◽  
Navigation Systems ◽  
Inertial Navigation Systems ◽  
Cfd Models ◽  
Air Turbulence ◽  
Wide Range ◽  
Wake Patterns ◽  
Board Ship

This paper presents the development of a wireless instrumentation system for estimation of air turbulence patterns in real-time. The proposed system uses off-the-shelf RC helicopter flying in wind turbulent regions and uses the oscillations caused by wind gusts to measure turbulence. This paper presents the proposed system as a tool to measure off-board ship air wake patterns generated by a cruising naval patrol craft. Two aviation grade Inertial Navigation Systems (INS) with onboard filters are used in this system. These filters precisely measure the dynamics and the location of the helicopter with respect to the vessel. The data is then wirelessly transmitted to a base station on the vessel where Back Propagation neural networks are used to remove the effects of pilot inputs from vibrational data in real time to extract the oscillations caused by the turbulence alone. The system was tested in Chesapeake Bay in a wide range of wind conditions and the results are shown as air wake intensity patterns plotted on helicopter trajectory around the cruising vessel. The proposed system will be used for experimental validation of CFD models to predict ship air wakes.

scholarly journals Improving Real-Time Hand Gesture Recognition with Semantic Segmentation

Sensors ◽  
2021 ◽  
Vol 21 (2) ◽  
pp. 356
Author(s):  
Gibran Benitez-Garcia ◽  
Lidia Prudente-Tixteco ◽  
Luis Carlos Castro-Madrid ◽  
Rocio Toscano-Medina ◽  
Jesus Olivares-Mercado ◽  
...  
Keyword(s):  
Optical Flow ◽  
Real Time ◽  
Gesture Recognition ◽  
Computational Cost ◽  
Semantic Segmentation ◽  
Hand Gesture Recognition ◽  
Hand Gesture ◽  
Temporal Shift ◽  
Time Performance ◽  
Wide Range

Hand gesture recognition (HGR) takes a central role in human–computer interaction, covering a wide range of applications in the automotive sector, consumer electronics, home automation, and others. In recent years, accurate and efficient deep learning models have been proposed for real-time applications. However, the most accurate approaches tend to employ multiple modalities derived from RGB input frames, such as optical flow. This practice limits real-time performance due to intense extra computational cost. In this paper, we avoid the optical flow computation by proposing a real-time hand gesture recognition method based on RGB frames combined with hand segmentation masks. We employ a light-weight semantic segmentation method (FASSD-Net) to boost the accuracy of two efficient HGR methods: Temporal Segment Networks (TSN) and Temporal Shift Modules (TSM). We demonstrate the efficiency of the proposal on our IPN Hand dataset, which includes thirteen different gestures focused on interaction with touchless screens. The experimental results show that our approach significantly overcomes the accuracy of the original TSN and TSM algorithms by keeping real-time performance.

Sky Segmentation for Enhanced Depth Reconstruction and Bokeh Rendering with Efficient Architectures

2020 ◽  
Vol 2020 (14) ◽  
pp. 378-1-378-7
Author(s):  
Tyler Nuanes ◽  
Matt Elsey ◽  
Radek Grzeszczuk ◽  
John Paul Shen
Keyword(s):  
Real Time ◽  
Mobile Device ◽  
Computational Cost ◽  
False Positives ◽  
Compact Model ◽  
High Quality ◽  
False Negatives ◽  
Trade Off ◽  
Depth Reconstruction ◽  
Binary Classifiers

We present a high-quality sky segmentation model for depth refinement and investigate residual architecture performance to inform optimally shrinking the network. We describe a model that runs in near real-time on mobile device, present a new, highquality dataset, and detail a unique weighing to trade off false positives and false negatives in binary classifiers. We show how the optimizations improve bokeh rendering by correcting stereo depth misprediction in sky regions. We detail techniques used to preserve edges, reject false positives, and ensure generalization to the diversity of sky scenes. Finally, we present a compact model and compare performance of four popular residual architectures (ShuffleNet, MobileNetV2, Resnet-101, and Resnet-34-like) at constant computational cost.

Sign in / Sign up

Export Citation Format

Share Document